12 papers
Not All Criteria Matter: Importance-Aware Criteria Weighting for Rubric-Based LLM Evaluation
Haocheng Yang, Licheng Pan, Yiming Dong +7
Rubric-based evaluation assesses the responses of large language models (LLMs) by aggregating the verification results of explicit criteria, yet not all criteria matter equally. Ho…
Learning the Pareto Frontier of Predictive Models under Distribution Shift
Yiming Dong, Jiwei Zhao, Yang Young Lu
Modern machine learning pipelines increasingly rely on reusing pretrained and foundation models across downstream tasks. These pretrained models can differ not only in performance…
Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers
Liangyu Wang, Siqi Zhang, Junjie Wang +7
The scaling of Large Language Models (LLMs) drives interest in matrix-based optimizers (e.g., Shampoo, Muon, SOAP) for their convergence efficiency; yet their requirement for holis…
Convergence Rate Analysis of the AdamW-style Shampoo: Unifying One-Sided and Two-Sided Preconditioning
Huan Li, Yiming Dong, Zhouchen Lin
This paper studies AdamW-style Shampoo, an effective variant of the classical Shampoo that won the external tuning track of the AlgoPerf neural network training competition. Our an…
Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
Zhoutong Wu, Yuan Zhang, Yiming Dong +4
Transformer models have driven breakthroughs across various language tasks by their strong capability to learn rich contextual representations. Scaling them to improve representati…
Conda: Column-Normalized Adam for Training Large Language Models Faster
Junjie Wang, Pan Zhou, Yiming Dong +6
Large language models (LLMs) have demonstrated impressive generalization and emergent capabilities, yet their pre-training remains computationally expensive and sensitive to optimi…
SADA: Safe and Adaptive Aggregation of Multiple Black-Box Predictions in Semi-Supervised Learning
Jiawei Shan, Zhifeng Chen, Yiming Dong +2
Semi-supervised learning (SSL) arises in practice when labeled data are scarce or expensive to obtain, while large quantities of unlabeled data are readily available. With the grow…
P/D-Device: Disaggregated Large Language Model between Cloud and Devices
Yibo Jin, Yixu Xu, Yue Chen +27
Serving disaggregated large language models has been widely adopted in industrial practice for enhanced performance. However, too many tokens generated in decoding phase, i.e., occ…
Stepsize anything: A unified learning rate schedule for budgeted-iteration training
Anda Tang, Yiming Dong, Yutao Zeng +2
The expanding computational costs and limited resources underscore the critical need for budgeted-iteration training, which aims to achieve optimal learning within predetermined it…
On the Convergence Rate of AdamW Measured by Norm
Huan Li, Yiming Dong, Zhouchen Lin
As the default optimizer for training large language models, AdamW has achieved remarkable success in deep learning. However, its convergence behavior is not theoretically well-und…
Convergence Rate Analysis of LION
Yiming Dong, Huan Li, Zhouchen Lin
The LION (evoLved sIgn mOmeNtum) optimizer for deep neural network training was found by Google via program search, with the simple sign update yet showing impressive performance i…
On the Convergence Rate of RMSProp and Its Momentum Extension Measured by Norm
Huan Li, Yiming Dong, Zhouchen Lin
Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with…